Abstract Models are among the most essential tools in robotics, such as kinematics and
dynamics models of the robot's own body and controllable external objects. It is widely …

A generally intelligent agent faces a dilemma: it requires a complex sensorimotor space to
be capable of solving a wide range of problems, but many tasks are only feasible given the …

A key challenge in scaling up robot learning to many skills and environments is removing
the need for human supervision, so that robots can collect their own data and improve their …

This paper studies systematic exploration for reinforcement learning (RL) with rich
observations and function approximation. We introduce contextual decision processes …

Reinforcement learning provides a powerful and flexible framework for automated
acquisition of robotic motion skills. However, applying reinforcement learning requires a …

This work considers a computationally and statistically efficient parameter estimation method
for a wide class of latent variable models—including Gaussian mixture models, hidden …

Recent approaches in robot perception follow the insight that perception is facilitated by
interaction with the environment. These approaches are subsumed under the term …

Many real-world problems involve the optimization of multiple, possibly conflicting
objectives. Multi-objective reinforcement learning (MORL) is a generalization of standard …

This paper introduces a simple efficient learning algorithms for general sequential decision
making. The algorithm combines Optimism for exploration with Maximum Likelihood …

We propose a theoretical framework for approximate planning and learning in partially
observed systems. Our framework is based on the fundamental notion of information state …